Magnetic resonance imaging (MRI) is a leading modality for the diagnosis of liver cancer, significantly improving the classification of the lesion and patient outcomes. However, traditional MRI faces challenges including risks from contrast agent (CA) administration, time-consuming manual assessment, and limited annotated datasets. To address these limitations, we propose a Time-Conditioned Autoregressive Contrast Enhancement (T-CACE) framework for synthesizing multi-phase contrast-enhanced MRI (CEMRI) directly from non-contrast MRI (NCMRI). T-CACE introduces three core innovations: a conditional token encoding (CTE) mechanism that unifies anatomical priors and temporal phase information into latent representations; and a dynamic time-aware attention mask (DTAM) that adaptively modulates inter-phase information flow using a Gaussian-decayed attention mechanism, ensuring smooth and physiologically plausible transitions across phases. Furthermore, a constraint for temporal classification consistency (TCC) aligns the lesion classification output with the evolution of the physiological signal, further enhancing diagnostic reliability. Extensive experiments on two independent liver MRI datasets demonstrate that T-CACE outperforms state-of-the-art methods in image synthesis, segmentation, and lesion classification. This framework offers a clinically relevant and efficient alternative to traditional contrast-enhanced imaging, improving safety, diagnostic efficiency, and reliability for the assessment of liver lesion.

Medical image synthesis plays a crucial role in clinical workflows, addressing the common issue of missing imaging modalities due to factors such as extended scan times, scan corruption, artifacts, patient motion, and intolerance to contrast agents. The paper presents a novel image synthesis network, the Pyramid Hierarchical Masked Diffusion Model (PHMDiff), which employs a multi-scale hierarchical approach for more detailed control over synthesizing high-quality images across different resolutions and layers. Specifically, this model utilizes randomly multi-scale high-proportion masks to speed up diffusion model training, and balances detail fidelity and overall structure. The integration of a Transformer-based Diffusion model process incorporates cross-granularity regularization, modeling the mutual information consistency across each granularity’s latent spaces, thereby enhancing pixel-level perceptual accuracy. Comprehensive experiments on two challenging datasets demonstrate that PHMDiff achieves superior performance in both the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), highlighting its capability to produce high-quality synthesized images with excellent structural integrity. Ablation studies further confirm the contributions of each component. Furthermore, the PHMDiff model, a multi-scale image synthesis framework across and within medical imaging modalities, shows significant advantages over other methods. The source code will be released with the paper. The source code is available at https://github.com/xiaojiao929/PHMDiff

In this paper, we offer a new visualization tool -- Dataset Statistical View (DSV), to lower the barrier of research entry by providing easy access to the question-answering (QA) datasets that researchers can build their work upon. Our target users are new researchers to the QA domain with no prior knowledge nor programming skills. The system is populated with multiple QA datasets, which covers a wide range of QA tasks. It allows researchers to explore and compare existing QA datasets at a one-stop website. The system shows statistical graphs for each QA dataset to offer an overview and a visual comparison between datasets. Although this paper focuses mainly at the syntactic level comparison, integrating bias and semantic level analysis is our ongoing work. We believe our DSV system is a valuable contribution to the advancement of the QA field, as it provides a solid starting point for new researchers and practitioners. An overview of the framework is demonstrated in this paper and the introduction of the application system is available at https://cnchuy.github.io/images/demo.mp4.

In this paper, we demonstrate an approach for question-answering pair generation primarily based on named entities using TV series data. Our generator provides a task based pipeline abstraction, which can be interpreted by a simple method where a context paragraph is passed as an input argument to the pipeline and the output is generated based on the task selected. We currently implemented three tasks for the pipeline which includes the following - i) qg - single question generation, ii) multi-qa-qg for multiple QA pairs generation and iii) e2e-qg for end to end QA pair generation.

Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data is to provide acoustic information as an additional learning signal. When generating speech, modifying this acoustic information enables multiple distinct renditions of a text to be produced. Since much of the unexplained variation is in the prosody, we propose a model that generates speech explicitly conditioned on the three primary acoustic correlates of prosody: $F_{0}$, energy and duration. The model is flexible about how the values of these features are specified: they can be externally provided, or predicted from text, or predicted then subsequently modified. Compared to a model that employs a variational auto-encoder to learn unsupervised latent features, our model provides more interpretable, temporally-precise, and disentangled control. When automatically predicting the acoustic features from text, it generates speech that is more natural than that from a Tacotron 2 model with reference encoder. Subsequent human-in-the-loop modification of the predicted acoustic features can significantly further increase naturalness.

The aim of clinical decision support implementing electronic health records is to satisfy the physicians' information needs. We are motivated to propose a self-attention based network on query expansion. Considering the difficulty and cost of medical text annotation and inspired by the idea of migration learning, we choose the Semantic Textual Similarity dataset for model training. Different from the previous work, the proposed approach is not only considering the score of a single term as an expansion term, but also taking the score of term combination into account. Our model utilizes Convolutional Neural Networks (CNN) to obtain sentence representation and self-attention mechanism for entity representation. With self-attention, it is able to estimate the weight of each entity to learn better representation for all entities. We conduct the experiments on three standard datasets of Text REtrieval Conference Clinical Decision Support Track, where the approach has a promising overall performance over the strong baselines.

Aspect-level sentiment classification aims to predict the sentiment polarity of a given aspect in a sentence. However, most of the existing methods focus on the information of the entire sentence rather than a segment that describes the aspect, making it difficult to identify the mapping between an aspect and a segment. Moreover, these methods are prone to the noise in the sentence. To alleviate this problem, we propose a novel approach that models the specific segments for aspect-level sentiment classification in a reinforcement learning framework. Our approach consists of two parts: an aspect segment extraction (ASE) model and an aspect sentiment classification (ASC) model. Specifically, the ASE model extracts the corresponding segment with reinforcement learning and feeds the extracted segment into the ASC model. Then, the ASC model makes the segment-level prediction and provides rewards to the ASE model. The experimental results indicate that our proposed approach can extract the segment towards the aspect effectively, and thus obtains competitive performance. Furthermore, we provide an intuitive understanding of why our ASE model is more effective for aspect-level sentiment classification via case studies.

Feature learning and selection have been widely applied in many research areas because of their good performance and lower complexity. Traditional methods usually treat all terms with same feature sets, such that performance can be damaged when noisy information is brought via wrong features for a given term. In this paper, we propose a term-based personalization approach to finding the best features for each term. First, features are given as the input so that we focus on selection strategies. Second, the importance of each feature subset to a given term is evaluated by the term-feature probabilistic relevance model. We present a feature searching method to generate feature candidate subsets for each term, since evaluating all the possible feature subsets is computationally intensive. Finally, we obtain the personalized feature set for each term as a subset of all features. Experiments have been conducted on the NICTA Synthetic Nursing Handover dataset and the results show that our approach is promising and effective.

The recurrent neural networks (RNNs) have shown good performance for sentence similarity modeling in recent years. Most RNNs focus on modeling the hidden states based on the current sentence, while the context information from the other sentence is not well investigated during the hidden state generation. In this paper, we propose a context-aligned RNN (CA-RNN) model, which incorporates the contextual information of the aligned words in a sentence pair for the inner hidden state generation. Specifically, we first perform word alignment detection to identify the aligned words in the two sentences. Then, we present a context alignment gating mechanism and embed it into our model to automatically absorb the aligned words' context for the hidden state update. Experiments on three benchmark datasets, namely TREC-QA and WikiQA for answer selection and MSRP for paraphrase identification, show the great advantages of our proposed model. In particular, we achieve the new state-of-the-art performance on TREC-QA and WikiQA. Furthermore, our model is comparable to if not better than the recent neural network based approaches on MSRP.

We mainly investigate word influence in neural sentiment classification, which results in a novel approach to promoting word sentiment and negation as attentions. Particularly, a sentiment and negation neural network (SNNN) is proposed, including a sentiment neural network (SNN) and a negation neural network (NNN). First, we modify the word level by embedding the word sentiment and negation information as the extra layers for the input. Second, we adopt a hierarchical LSTM model to generate the word-level, sentence-level and document-level representations respectively. After that, we enhance word sentiment and negation as attentions over the semantic level. Finally, the experiments conducting on the IMDB and Yelp data sets show that our approach is superior to the state-of-the-art baselines. Furthermore, we draw the interesting conclusions that (1) LSTM performs better than CNN and RNN for neural sentiment classification; (2) word sentiment and negation are a strong alliance with attention, while overfitting occurs when they are simultaneously applied at the embedding layer; and (3) word sentiment/negation can be singly implemented for better performance as both embedding layer and attention at the same time.

People without medical background usually seek health information from Web search engines using queries with the circumlocutory style, such as a description of observations, instead of professional symptoms or medical terms. However, the existing commercial search engines performs better on professional terms than the nonprofessional ones. Therefore, we propose an interaction-embedded framework for healthcare search to fit this gap. First, we absorb the MeSH and Wikipedia data as the knowledge resources to translate the circumlocutory queries into medical related terminologies. Then, we embed the user interaction into the search process to better capture users' intents. Finally, we perform a series of experiments on the TREC and CLEF eHealth collections for evaluation purpose. The experimental results show that our proposed framework are promising and outperforms the traditional retrieval algorithms.

This paper presents a notion of location-sensitive online-offline hybrid social system. What makes it distinct from other mobile social media is that it supports not simply online interaction but also online-offline hybrid interaction, and location sensitivity is a feature designed to lower cost for users to participant in offline activities. We designed and implemented a prototype mobile Application called USee, and danmaku - an emerging socio-digital paradigm, was employed as the main user interface. We introduce the design and implementation of USee, and conduct a preliminary study to understand how it works in reality. Findings of the preliminary study suggest promises of the notion of location-sensitive online-offline hybrid social system. We highlight that USee provides users a free and safe social place, in which users express high and unique enthusiasm and engagement. This paper contributes to provide meaningful insights and design implication to mobile social media.

The neural networks have attracted great attention for sentence similarity modeling in recent years. Most neural networks focus on the representation of each sentence, while the common features of a sentence pair are not well studied. In this paper, we propose a Collaborative and Adversarial Network (CAN), which explicitly models the common features between two sentences for enhancing sentence similarity modeling. To be specific, a common feature extractor is presented and embedded into our CAN model, which includes a generator and a discriminator playing a collaborative and adversarial game for common feature extraction. Experiments on three benchmark datasets, namely TREC-QA and WikiQA for answer selection and MSRP for paraphrase identification, show that our proposed model is effective to boost the performance of sentence similarity modeling. In particular, our proposed model outperforms the state-of-the-art approaches on TREC-QA without using any external resources or pre-training. For the other two datasets, our model is also comparable to if not better than the recent neural network approaches.

Query expansion under the pseudo-relevance feedback (PRF) framework has been extensively studied in information retrieval. However, most expansion methods are mainly based on the statistics of single terms, which can generate plenty of irrelevant query terms and decrease retrieval performance. To alleviate this problem, we propose an approach that adapts the PRF-based contextual snippets into a context-aware topic model to enhance query representations. Specifically, instead of selecting a series of independent terms, we make full use of the query contextual information and focus on the snippets with the length ofnin the PRF documents. Furthermore, we propose a context-aware topic (CAT) model to mine the topic distributions of the query-relevant snippets, namely, fine contextual snippets. In contrast to the traditional topic models that infer the topics from the whole corpus, we establish a bridge between the snippets and the corresponding PRF documents, which can be used for modeling the topics more precisely and efficiently. Finally, the topic distributions of the fine snippets are used for context-aware and topic-sensitive query representations. To evaluate the performance of our approach, we integrate the obtained queries into a topic-based hybrid retrieval model and conduct extensive experiments on various TREC collections. The experimental results show that our query-modeling approach is more effective in boosting retrieval performance compared with the state-of-the-art methods.

Temporal information has been widely used to promote the information retrieval (IR) performance, especially for microblog search which usually prefers the latest news and events. Previous studies mainly focused on incorporating the document-level temporal information into retrieval, while the temporal relevance of each query word was not well investigated. In this paper, we propose a word temporal predictor to characterize the word-level temporal relevance by fine-grained time-aware kernel density estimation over the feedback documents. In addition, we present a fine-grained time-aware framework to integrate the proposed word temporal predictor with the traditional document temporal predictor for retrieval. Finally, we incorporate the framework into two state-of-the-art retrieval models, namely language model (LM) and BM25. The experimental results on the TREC 2011-2014 Microblog collections, show that our proposed word temporal predictor is effective to boost the retrieval performance within both LM and BM25 frameworks. In particular, we achieve significant improvements over the strong baselines with optimized settings in most cases. Furthermore, our fine-grained time-aware models with word temporal predictor are comparable to if not better than the state-of-the-art temporal retrieval models.

Clinical Decision Systems utilize patient profiles to search for relevant medical support. Existing work on medical search has a primary topic on query expansion, which enriches queries by adding more useful terms. However, it performs well when queries are concise. In this paper, we aim to tackle verbose queries and propose a new automatic query reformulation method, which not only considers query expansion, but also includes query reduction. This improves the searching performance by refining the query to effectively avoid irrelevant results. The method is achieved by classifying each sentence into expansion and reduction categories with a weighted score model, which depends on the occurrence of medical and negative terms. The refined queries show promising results on experiments with TREC CDS datasets. In particular, the final performance makes improvements in terms of NDCG as 8.2% compared to the prevailing query expansion method, and 22.07% compared to the baseline of original query.

Attention based recurrent neural networks (RNN) have shown a great success for question answering (QA) in recent years. Although significant improvements have been achieved over the non-attentive models, the position information is not well studied within the attention-based framework. Motivated by the effectiveness of using the word positional context to enhance information retrieval, we assume that if a word in the question (i.e., question word) occurs in an answer sentence, the neighboring words should be given more attention since they intuitively contain more valuable information for question answering than those far away. Based on this assumption, we propose a positional attention based RNN model, which incorporates the positional context of the question words into the answers' attentive representations. Experiments on two benchmark datasets show the great advantages of our proposed model. Specifically, we achieve a maximum improvement of 8.83% over the classical attention based RNN model in terms of mean average precision. Furthermore, our model is comparable to if not better than the state-of-the-art approaches for question answering.

Here we propose an advance Skip-gram model to incorporate both word sentiment and negation information. In particular, there is a a softmax layer for the word sentiment polarity upon the Skip-gram model. Then, two paralleled embedding layers are set up in the same embedding space, one for the affirmative context and the other for the negated context, followed by their loss functions. We evaluate our proposed model on the 2013 and 2014 SemEval data sets. The experimental results show that the proposed approach achieves better performance and learns higher dimensional word embedding informatively on the large-scale data.

We propose a semi-informative aware approach using the topic model on query expansion problem in the biomedicine domain. the demographics and disease information is applied to semi-structure the topic model as the “known” label, compared to the traditional latent topics in topic modelling. Then, we suggest to select three terms from the top ranked documents to expand the query, based on the assumption in the pseudo relevance feedback method that the top ranked results in the first retrieval around are relevant. After that, we conduct the experiments on the TREC medical records data sets with extensive analysis and discussions. Numerically, we achieve the improvements of 7.41% on MAP, 9.29% on Bpref and 5.60% on P@10 respectively over the strong baselines.

Computer aid technology is widely applied in decision-making and outcome assessment of healthcare delivery, in which modeling knowledge and expert experience is technically important. However, the conventional rule-based models are incapable of capturing the underlying knowledge because they are incapable of simulating the complexity of human brains and highly rely on feature representation of problem domains. Thus we attempt to apply a deep model to overcome this weakness. The deep model can simulate the thinking procedure of human and combine feature representation and learning in a unified model. A modified version of convolutional deep belief networks is used as an effective training method for large-scale data sets. Then it is tested by two instances: a dataset on hypertension retrieved from a HIS system, and a dataset on Chinese medical diagnosis and treatment prescription from a manual converted electronic medical record (EMR) database. The experimental results indicate that the proposed deep model is able to reveal previously unknown concepts and performs much better than the conventional shallow models.

Our slogan for the proposed Clairvoyant system is "with several clicks, the future is in your hand, the plan comes into your mind". Clairvoyant is to predict the future of new videos with only few data. The core function in the system is the novel shifted shape match prediction algorithm, based on a K-Nearest Neighbor model. Tons of experiments have been conducted on the open data sets. The experimental results confirms that the proposed SSMP algorithm is promising and outperforms the baselines with significant improvements on various evaluation methods. A demonstration video has been published at http://1drv.ms/1nyH3hD.

BACKGROUND: The growth of the biomedical information requires most information retrieval systems to provide short and specific answers in response to complex user queries. Semantic information in the form of free text that is structured in a way makes it straightforward for humans to read but more difficult for computers to interpret automatically and search efficiently. One of the reasons is that most traditional information retrieval models assume terms are conditionally independent given a document/passage. Therefore, we are motivated to consider term associations within different contexts to help the models understand semantic information and use it for improving biomedical information retrieval performance. RESULTS: We propose a term association approach to discover term associations among the keywords from a query. The experiments are conducted on the TREC 2004-2007 Genomics data sets and the TREC 2004 HARD data set. The proposed approach is promising and achieves superiority over the baselines and the GSP results. The parameter settings and different indices are investigated that the sentence-based index produces the best results in terms of the document-level, the word-based index for the best results in terms of the passage-level and the paragraph-based index for the best results in terms of the passage2-level. Furthermore, the best term association results always come from the best baseline. The tuning number k in the proposed recursive re-ranking algorithm is discussed and locally optimized to be 10. CONCLUSIONS: First, modelling term association for improving biomedical information retrieval using factor analysis, is one of the major contributions in our work. Second, the experiments confirm that term association considering co-occurrence and dependency among the keywords can produce better results than the baselines treating the keywords independently. Third, the baselines are re-ranked according to the importance and reliance of latent factors behind term associations. These latent factors are decided by the proposed model and their term appearances in the first round retrieved passages.

Modeling and mining term association is important for information retrieval, which allows an information retrieval system to retrieve relevant documents/passages more precisely. In this paper, we propose a new approach for discovering term associations among the keywords from a query. First, factor analysis is applied to discover some hidden common factors as the "eliteness" variables that can be used to estimate the importance of term associations. Second, a factor analysis based model and a corresponding algorithm are proposed. Then, we report experimental results that confirm the effectiveness and superiority of the proposed term association approach. Our approach achieves excellent results on the TREC 2007 and 2006 data sets, which provides a promising avenue for constructing high performance information retrieval systems.

BACKGROUND: The users desire to be provided short, specific answers to questions and put them in context by linking original sources from the biomedical literature. Through the use of information retrieval technologies, information systems retrieve information to index data based on all kinds of pre-defined searching techniques/functions such that various ranking strategies are designed depending on different sources. In this paper, we propose a robust approach to optimizing multi-source information for improving genomics retrieval performance. RESULTS: In the proposed approach, we first consider a common scenario for a metasearch system that has access to multiple baselines with retrieving and ranking documents/passages by their own models. Then, given selected baselines from multiple sources, we investigate three modified fusion methods in the proposed approach, reciprocal, CombMNZ and CombSUM, to re-rank the candidates as the outputs for evaluation. Our empirical study on both 2007 and 2006 genomics data sets demonstrates the viability of the proposed approach for obtaining better performance. Furthermore, the experimental results show that the reciprocal method provides notable improvements on the individual baseline, especially on the passage2-level MAP and the aspect-level MAP. CONCLUSIONS: From the extensive experiments on two TREC genomics data sets, we draw the following conclusions. For the three fusion methods proposed in the robust approach, the reciprocal method outperforms the CombMNZ and CombSUM methods obviously, and CombSUM works well on the passage2-level when compared with CombMNZ. Based on the multiple sources of DFR, BM25 and language model, we can observe that the alliance of giants achieves the best result. Meanwhile, under the same combination, the better the baseline performance is, the more contribution the baseline provides. These conclusions are very useful to direct the fusion work in the field of biomedical information retrieval.

In this paper, we focus on the biomedicine domain to propose a multi-source fusion approach for improving information retrieval performance. First, we consider a common scenario for a metasearch system that has access to multiple baselines with retrieving and ranking documents/passages by their own models. Second, given selected baselines from multiple sources, we employ two modified fusion rules in the proposed approach, reciprocal and combMNZ, to rerank the candidates as the output for evaluation. Third, our empirical study on both 2007 and 2006 genomics data sets demonstrates the viability of the proposed approach to better performance fusion. Fourth, the experimental results show that the reciprocal method provides notable improvements on the individual baseline, especially on the effective passage MAP, the passage2-level and the diversity MAP, the aspect-level.

their patients' records from paper to computer, enormous amounts of electronic medical records (EMR) have become available for medical research. Some of the EMR data are well-structured, for which traditional database management systems can provide effective retrieval and management functions. However, most of the EMR data (such as progress notes and consultation letters) are in free text formats. How to effectively and efficiently retrieve and discover useful information from the vast amount of such semi-structured data is a challenge faced by medical professionals. Without proper tools, the rich information and knowledge buried in the medical health records are unavailable for clinical research and decision-making. The objective of our research is to develop text analytics tools that are capable of parsing clinical medical data so that predefined search subjects that correspond to a list of medical diagnoses can be extracted. In addition to this particular core functionality, it is also desired that several important assets should be present within the text-analytics tools in order to improve its overall ability to be used as recommendation tools. In this research, we work with research scientists at the Institute for Clinical Evaluative Sciences (ICES) in Toronto and examine a number of techniques for structuring and processing free text documents in order to effectively and efficiently search and analyze vast amount of medical records. We implement several powerful medical text analytics tools for clinical data searching and classification. For data classification, our tools sort through a great amount of patientrecords to identify the likelihood of a patient having myocardial infarction (MI) or hypertension (HTN), and classify the patients accordingly. Our tools can also identify the likelihood of a patient being a smoker, previous smoker or non-smoker based on the text data of medical records.

In this paper, we propose a Bayesian learning approach to promoting diversity for information retrieval in biomedicine and a re-ranking model to improve retrieval performance in the biomedical domain. First, the re-ranking model computes the maximum posterior probability of the hidden property corresponding to each retrieved passage. Then it iteratively groups the passages into subsets according to their properties. Finally, these passages are re-ranked from the subsets as our output. There is no need for our proposed method to use any external biomedical resource. We evaluate our Bayesian learning approach by conducting extensive experiments on the TREC 2004-2007 Genomics data sets. The experimental results show the effectiveness of the proposed Bayesian learning approach for promoting diversity in ranking for biomedical information retrieval on four years TREC data sets.

In this paper, we propose a reranking model to improve the aspect-level performance in the biomedical domain. This model iteratively computes the maximum hidden aspect for every retrieved passage and then reranks these passages from aspect subsets. The experimental results show the improvements of the aspect-level performance up to 27.14% for 2006 Genomics topics and 27.09% for 2007 Genomics topics.